© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105087
    Prev
    Next
    INDEX
    Explanations

    future outcomes and possibilities

    np_acts-logits-general · gemini-2.5-flash-lite

    instructions and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     같이
    0.48
     iguales
    0.47
     oreilles
    0.44
    ⟋
    0.43
    application
    0.43
    PASSWORD
    0.43
    music
    0.42
     literals
    0.42
     Archived
    0.42
     bushy
    0.42
    POSITIVE LOGITS
    ócio
    0.47
    ất
    0.47
    ían
    0.47
    ßen
    0.47
    چنین
    0.47
    Ens
    0.47
    Ᏺ
    0.46
     disposer
    0.46
    𝙊
    0.46
     संभालने
    0.45
    Activations Density 0.000%

    No Known Activations